Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition

Zheng Yuan, Chuanqi Tan, Songfang Huang, Fei Huang


Abstract
Nested entities are observed in many domains due to their compositionality, which cannot be easily recognized by the widely-used sequence labeling framework.A natural solution is to treat the task as a span classification problem.To learn better span representation and increase classification performance, it is crucial to effectively integrate heterogeneous factors including inside tokens, boundaries, labels, and related spans which could be contributing to nested entities recognition.To fuse these heterogeneous factors, we propose a novel triaffine mechanism including triaffine attention and scoring.Triaffine attention uses boundaries and labels as queries and uses inside tokens and related spans as keys and values for span representations.Triaffine scoring interacts with boundaries and span representations for classification.Experiments show that our proposed method outperforms previous span-based methods, achieves the state-of-the-art F1 scores on nested NER datasets GENIA and KBP2017, and shows comparable results on ACE2004 and ACE2005.
Anthology ID:
2022.findings-acl.250
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venues:
ACL | Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3174–3186
Language:
URL:
https://aclanthology.org/2022.findings-acl.250
DOI:
10.18653/v1/2022.findings-acl.250
Bibkey:
Cite (ACL):
Zheng Yuan, Chuanqi Tan, Songfang Huang, and Fei Huang. 2022. Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition. In Findings of the Association for Computational Linguistics: ACL 2022, pages 3174–3186, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition (Yuan et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-acl.250.pdf
Software:
 2022.findings-acl.250.software.zip
Code
 GanjinZero/Triaffine-nested-ner
Data
ACE 2004ACE 2005GENIA